Epistemic Network Analysis in Data Studies

undefined
 
Epistemic Network Analysis
 
Week 5 Video 6
 
Today’s Class
 
Epistemic Network Analysis
Epistemic Network Analysis (ENA)
(Shaffer, 2017)
 
Studying relationships between elements in coded
data
 
Lots of applications
 
Conference founded around this method
(in large part)
International Conference on Quantitative Ethnography
 
Nodes and links
 
Nodes = occurrences of the codes
Links = co-occurrences of the codes
 
Let’s start with an example
 
Chosen primarily because I understand it well
 
Analyzing Quitting Behavior
(Karumbaiah et al., 2019)
 
Comparing students who quit a level in the game
Physics Playground 
to students who do not quit a
game level
In terms of the gameplay actions each group of
students makes
 
Nodes and links
 
Nodes are behaviors
Links represent when a player demonstrates both
behaviors in one session playing one level
 
Nodes and links
 
When red students draw.freeform, they also erase
Less commonly, when they draw.freeform, they also
nudge
 
When green students
draw.freeform, they also ramp
Less commonly, when they
nudge, they also ramp
 
Comparing groups in data
 
In this case,
red= people who quit a game
green = people who do not quit
 
 
Can Compare Graphs Between
Contexts (here: game levels)
 
Interpreting the graphs in
(Karumbaiah et al., 2019)
 
Can seem tricky
Very powerful when you dig into the graphs
 
Key Themes
 identified by Karumbaiah
et al. (2019)
 
Identifying Key Action
Missing Identification of Supporting Objects
Over-reliance on Nudge
Limited Early Action Expansion and Later Action
Convergence
 
Identifying Key Action
 
I
n
d
i
c
a
t
e
s
 
t
h
e
i
r
 
l
a
c
k
 
o
f
 
c
o
n
c
e
p
t
u
a
l
 
u
n
d
e
r
s
t
a
n
d
i
n
g
 
o
f
 
P
h
y
s
i
c
s
 
Missing Identification of Supporting
Objects
 
Over-reliance on Nudge
 
I
n
d
i
c
a
t
e
s
 
p
o
t
e
n
t
i
a
l
 
w
h
e
e
l
 
s
p
i
n
n
i
n
g
 
t
e
n
d
e
n
c
i
e
s
 
Limited Early Action Expansion and
Later Action Convergence
 
Need Fulcrum
 
Note
 
We looked at these graphs qualitatively, but
statistical analysis of differences is possible too
Is link A stronger than link B?
Is link Q stronger in group R or group S?
 
Other examples
 
 
Studying connections between topics in
meetings over time (Nash & Shaffer, 2013)
 
 
Studying Process of Successful and Unsuccessful
Teams (Arastoopour et al., 2016)
 
 
Exploring Shifts in Student Identity over
Time (Barany & Foster, 2019)
 
Important setup questions
 
What makes a relationship “stronger”?
 
Important setup questions
 
What are your codes?
How did you derive those codes?
Behaviors in data
Text mining
Hand coding
Hand coding THEN text mining (nCoder+)
(Cai et al., 2019)
Collaborative mixed-initiative human-machine coding
(Codey) (Choi et al., 2022)
 
Important setup questions
 
Which codes do you display?
What are your aggregation units (stanzas)?
Everything a learner does together
Everything a learner does on a specific level together
Everyone in a group of learners/team
Everything in a piece of content
Everything in a meeting
 
Referred to as Stanza-Based
Interaction Data (Shaffer et al., 2016)
 
1.
A set of objects
2.
The way they relate to each other
3.
Grouped into a set of stanzas
4.
That reveal evidence about the relationships
between the objects
 
Important setup questions
 
One-directional relationships or bi-directional
relationships?
 
Usually bi-directional, but some work looks at one-
directional relationships over time
(Karumbaiah & Baker, 2020)
 
Important setup questions
 
What do the X and Y axes mean?
Typically determined empirically by collapsing the
feature space using SVD, singular value decomposition
Similar to factor analysis (week 7)
This approach can make X and Y hard to interpret but
best splits out the variables visually
 
ENA
 
Important method, growing in scope and community
applying it
 
Knowledge Graphs/Spaces
 
Another key application of network analysis
We will discuss next week
 
Next week
 
Structure Discovery
Slide Note
Embed
Share

Epistemic Network Analysis (ENA) is a method for studying relationships between elements in coded data with various applications. It involves analyzing nodes as occurrences of codes and links as co-occurrences of codes. Using examples like analyzing quitting behavior in a game, ENA can compare groups in data and interpret graphs to glean valuable insights. The International Conference on Quantitative Ethnography is a prominent platform for discussions centered around ENA methodology.

  • Epistemic Network Analysis
  • Data Studies
  • ENA Method
  • Relationships
  • Conference

Uploaded on Sep 11, 2024 | 0 Views


Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

E N D

Presentation Transcript


  1. Week 5 Video 6 Epistemic Network Analysis

  2. Todays Class Epistemic Network Analysis

  3. Epistemic Network Analysis (ENA) (Shaffer, 2017) Studying relationships between elements in coded data Lots of applications Conference founded around this method (in large part) International Conference on Quantitative Ethnography

  4. Nodes and links Nodes = occurrences of the codes Links = co-occurrences of the codes

  5. Lets start with an example Chosen primarily because I understand it well

  6. Analyzing Quitting Behavior (Karumbaiah et al., 2019) Comparing students who quit a level in the game Physics Playground to students who do not quit a game level In terms of the gameplay actions each group of students makes

  7. Nodes and links Nodes are behaviors Links represent when a player demonstrates both behaviors in one session playing one level

  8. Nodes and links When red students draw.freeform, they also erase Less commonly, when they draw.freeform, they also nudge When green students draw.freeform, they also ramp Less commonly, when they nudge, they also ramp

  9. Comparing groups in data In this case, red= people who quit a game green = people who do not quit

  10. Can Compare Graphs Between Contexts (here: game levels)

  11. Interpreting the graphs in (Karumbaiah et al., 2019) Can seem tricky Very powerful when you dig into the graphs

  12. Key Themes identified by Karumbaiah et al. (2019) Identifying Key Action Missing Identification of Supporting Objects Over-reliance on Nudge Limited Early Action Expansion and Later Action Convergence

  13. Identifying Key Action Indicates their lack of conceptual understanding of Physics

  14. Missing Identification of Supporting Objects

  15. Over-reliance on Nudge Indicates potential wheel spinning tendencies

  16. Limited Early Action Expansion and Later Action Convergence Need Fulcrum

  17. Note We looked at these graphs qualitatively, but statistical analysis of differences is possible too Is link A stronger than link B? Is link Q stronger in group R or group S?

  18. Other examples

  19. Studying connections between topics in meetings over time (Nash & Shaffer, 2013)

  20. Studying Process of Successful and Unsuccessful Teams (Arastoopour et al., 2016)

  21. Exploring Shifts in Student Identity over Time (Barany & Foster, 2019)

  22. Important setup questions What makes a relationship stronger ?

  23. Important setup questions What are your codes? How did you derive those codes? Behaviors in data Text mining Hand coding Hand coding THEN text mining (nCoder+) (Cai et al., 2019) Collaborative mixed-initiative human-machine coding (Codey) (Choi et al., 2022)

  24. Important setup questions Which codes do you display? What are your aggregation units (stanzas)? Everything a learner does together Everything a learner does on a specific level together Everyone in a group of learners/team Everything in a piece of content Everything in a meeting

  25. Referred to as Stanza-Based Interaction Data (Shaffer et al., 2016) A set of objects The way they relate to each other Grouped into a set of stanzas That reveal evidence about the relationships between the objects 1. 2. 3. 4.

  26. Important setup questions One-directional relationships or bi-directional relationships? Usually bi-directional, but some work looks at one- directional relationships over time (Karumbaiah & Baker, 2020)

  27. Important setup questions What do the X and Y axes mean? Typically determined empirically by collapsing the feature space using SVD, singular value decomposition Similar to factor analysis (week 7) This approach can make X and Y hard to interpret but best splits out the variables visually

  28. ENA Important method, growing in scope and community applying it

  29. Knowledge Graphs/Spaces Another key application of network analysis We will discuss next week

  30. Next week Structure Discovery

Related


More Related Content

giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#